What problem does it solve? Scientific hypotheses and arguments often suffer from confirmation bias, unfalsifiable claims, and untested robustness, leading to unreliable research conclusions. This Skill systematically stress-tests hypotheses and arguments before they are accepted as research claims. ## Core Features & Use Cases - Popper Falsifiability Testing: Checks whether a hypothesis has concrete, testable falsification conditions and flags unfalsifiable claims as speculative. - Bayesian Confidence Scoring: Updates prior to posterior confidence using evidence-quality-graded likelihood ratios, with a five-level verdict from strong support to strong opposition. - Robustness and Counterargument Analysis: Runs sensitivity checks across sample, method, population, and time dimensions, and enumerates at least three alternative explanations. - Use Case: Given a hypothesis like "a plasma biomarker predicts Alzheimer's disease 5-10 years early" with supporting evidence, the Skill produces a verification report with falsification conditions, posterior confidence, counterarguments, and a clear verdict such as insufficient_evidence. ## Quick Start Verify this hypothesis and its supporting argument using falsification testing, Bayesian confidence scoring, and robustness analysis, then output a verification report with a clear verdict.
